Noometry

Model comparison

GLM-4.7-Flash vs GPT-4 Turbo

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 30.5 on the Noometry Index.

Last verified . 19 shared benchmarks.

GLM-4.7-Flash Z.ai (Zhipu)

38.8

Rank #180 Confirmed

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GLM-4.7-Flash scores higher in 7 categories and GPT-4 Turbo in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.7-Flash leads 36.1 to 9.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 58.3% for GLM-4.7-Flash and 6.7% for GPT-4 Turbo.
  • GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • GLM-4.7-Flash accepts more context: 200K tokens versus 128K.
  • GLM-4.7-Flash has downloadable open weights; the other is API-only.

Side by side

GLM-4.7-FlashGPT-4 Turbo
ProviderZ.ai (Zhipu)OpenAI
Noometry Index38.830.5
Released2026-01-192023-11-06
WeightsOpenProprietary
Context window200K128K
Max output131K4K
Input $ / M tokens$0.06$10
Output $ / M tokens$0.40$30
Results tracked2136

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding GLM-4.7-Flash leads

GLM-4.7-Flash: 40.6 (#135), GPT-4 Turbo: 33.8 (#249)

BenchmarkGLM-4.7-FlashGPT-4 Turbo
LMArena Coding13831268
WeirdML—18%
BigCodeBench Instruct—48.2%
BigCodeBench Complete—58.2%
HumanEval+—86.6%
MBPP+—73.3%

Agentic & Tool Use Not comparable

GLM-4.7-Flash: —, GPT-4 Turbo: —

BenchmarkGLM-4.7-FlashGPT-4 Turbo
METR Time Horizons—36.7%

Reasoning GLM-4.7-Flash leads

GLM-4.7-Flash: 20.9 (#229), GPT-4 Turbo: 15.3 (#317)

BenchmarkGLM-4.7-FlashGPT-4 Turbo
Chess Puzzles0%6%
LMArena Hard Prompts13561251
SimpleBench—25.1%
DTBench—61.6%
LMCA—9.8%
Epoch Capabilities Index—127.25
ForecastBench—59.4

Math GLM-4.7-Flash leads

GLM-4.7-Flash: 36.1 (#173), GPT-4 Turbo: 9.0 (#322)

BenchmarkGLM-4.7-FlashGPT-4 Turbo
OTIS Mock AIME 2024-202558.3%6.7%
LMArena Math13551272
FrontierMath (Tiers 1-3)—0.7%
MATH Level 5—46.7%

Knowledge GLM-4.7-Flash leads

GLM-4.7-Flash: 35.5 (#184), GPT-4 Turbo: 24.3 (#268)

BenchmarkGLM-4.7-FlashGPT-4 Turbo
GPQA Diamond60.5%46.6%
LMArena Expert13571223
Confabulations—28.4%
Vectara Hallucination Rate9.3%—
MMLU—81.3%

Multimodal Not comparable

GLM-4.7-Flash: —, GPT-4 Turbo: 30.6 (#110)

BenchmarkGLM-4.7-FlashGPT-4 Turbo
LMArena Vision—1090

Multilingual GLM-4.7-Flash leads

GLM-4.7-Flash: 46.5 (#158), GPT-4 Turbo: 40.5 (#216)

BenchmarkGLM-4.7-FlashGPT-4 Turbo
LMArena Non-English13301245
LMArena Chinese14031242
LMArena French13321276
LMArena German13371259
LMArena Korean12831187
LMArena Russian13321259
LMArena Spanish13501260
LMArena Japanese—1194

Instruction Following GLM-4.7-Flash leads

GLM-4.7-Flash: 70.1 (#167), GPT-4 Turbo: 65.8 (#216)

BenchmarkGLM-4.7-FlashGPT-4 Turbo
LMArena Instruction Following13271249

Long Context GLM-4.7-Flash leads

GLM-4.7-Flash: 40.9 (#148), GPT-4 Turbo: 38.0 (#206)

BenchmarkGLM-4.7-FlashGPT-4 Turbo
LMArena Longer Query13451254

Writing & Preference Too close to call

GLM-4.7-Flash: 47.4 (#210), GPT-4 Turbo: 47.7 (#206)

BenchmarkGLM-4.7-FlashGPT-4 Turbo
LMArena Text13511272
LMArena Creative Writing12971269
LMArena Multi-Turn13421267
EQ-Bench Creative Writing1125—

Frequently asked questions

Is GLM-4.7-Flash better than GPT-4 Turbo?

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 30.5 on the Noometry Index.

Which is cheaper, GLM-4.7-Flash or GPT-4 Turbo?

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; GPT-4 Turbo lists at $10 and $30.

Is GLM-4.7-Flash or GPT-4 Turbo better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.6 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7-Flash does, with 200K tokens against 128K.

How many benchmarks do GLM-4.7-Flash and GPT-4 Turbo share?

19 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and GPT-4 Turbo has 36.

Related comparisons

Go deeper